A sequential learning algorithm for a spiking neural classifier

S. Dora, S. Suresh, N. Sundararajan

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Abstract This paper presents a biologically inspired, sequential learning spiking neural classifier (SLSNC) for pattern classification problems. It consists of a two layered neural network and a separate decision block which estimates the predicted class label. Inspired by observations in the neuroscience literature, the input layer employs a new neuron model which converts real valued stimuli into spikes with varying amplitudes and firing times. The intermediate layer neurons are modeled as integrate-and-fire spiking neurons. The decision block identifies that intermediate neuron which fires first and returns the class label associated with that neuron as the predicted class label. The sequential learning algorithm for the spiking neural network automatically determines the network structure from the training samples and adapts its synaptic weights by long term potentiation and long term depression. Performance of SLSNC has been evaluated using a number of benchmark classification problems and the results have been compared with other well-known spiking neural network classifiers in the literature as well as with the standard support vector machine (SVM) with a Gaussian kernel and the fast learning Extreme Learning Machine (ELM) classifiers. The results clearly indicate that the described spiking neural network produces similar or better generalization performance with a smaller network.

LanguageEnglish
Article number3090
Pages255-268
Number of pages14
JournalApplied Soft Computing Journal
Volume36
Early online date13 Aug 2015
DOIs
Publication statusPublished - 30 Nov 2015

Fingerprint

Learning algorithms
Neurons
Classifiers
Neural networks
Labels
Fires
Pattern recognition
Support vector machines
Learning systems

Keywords

  • 2-Dimensional coding
  • Pattern classification
  • Sequential learning
  • Spiking neural network

Cite this

Dora, S. ; Suresh, S. ; Sundararajan, N. / A sequential learning algorithm for a spiking neural classifier. In: Applied Soft Computing Journal. 2015 ; Vol. 36. pp. 255-268.
@article{8fc05d4e690044e2bb159cf3f7af9d16,
title = "A sequential learning algorithm for a spiking neural classifier",
abstract = "Abstract This paper presents a biologically inspired, sequential learning spiking neural classifier (SLSNC) for pattern classification problems. It consists of a two layered neural network and a separate decision block which estimates the predicted class label. Inspired by observations in the neuroscience literature, the input layer employs a new neuron model which converts real valued stimuli into spikes with varying amplitudes and firing times. The intermediate layer neurons are modeled as integrate-and-fire spiking neurons. The decision block identifies that intermediate neuron which fires first and returns the class label associated with that neuron as the predicted class label. The sequential learning algorithm for the spiking neural network automatically determines the network structure from the training samples and adapts its synaptic weights by long term potentiation and long term depression. Performance of SLSNC has been evaluated using a number of benchmark classification problems and the results have been compared with other well-known spiking neural network classifiers in the literature as well as with the standard support vector machine (SVM) with a Gaussian kernel and the fast learning Extreme Learning Machine (ELM) classifiers. The results clearly indicate that the described spiking neural network produces similar or better generalization performance with a smaller network.",
keywords = "2-Dimensional coding, Pattern classification, Sequential learning, Spiking neural network",
author = "S. Dora and S. Suresh and N. Sundararajan",
year = "2015",
month = "11",
day = "30",
doi = "10.1016/j.asoc.2015.06.062",
language = "English",
volume = "36",
pages = "255--268",
journal = "Applied Soft Computing",
issn = "1568-4946",
publisher = "Elsevier",

}

A sequential learning algorithm for a spiking neural classifier. / Dora, S.; Suresh, S.; Sundararajan, N.

In: Applied Soft Computing Journal, Vol. 36, 3090, 30.11.2015, p. 255-268.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A sequential learning algorithm for a spiking neural classifier

AU - Dora, S.

AU - Suresh, S.

AU - Sundararajan, N.

PY - 2015/11/30

Y1 - 2015/11/30

N2 - Abstract This paper presents a biologically inspired, sequential learning spiking neural classifier (SLSNC) for pattern classification problems. It consists of a two layered neural network and a separate decision block which estimates the predicted class label. Inspired by observations in the neuroscience literature, the input layer employs a new neuron model which converts real valued stimuli into spikes with varying amplitudes and firing times. The intermediate layer neurons are modeled as integrate-and-fire spiking neurons. The decision block identifies that intermediate neuron which fires first and returns the class label associated with that neuron as the predicted class label. The sequential learning algorithm for the spiking neural network automatically determines the network structure from the training samples and adapts its synaptic weights by long term potentiation and long term depression. Performance of SLSNC has been evaluated using a number of benchmark classification problems and the results have been compared with other well-known spiking neural network classifiers in the literature as well as with the standard support vector machine (SVM) with a Gaussian kernel and the fast learning Extreme Learning Machine (ELM) classifiers. The results clearly indicate that the described spiking neural network produces similar or better generalization performance with a smaller network.

AB - Abstract This paper presents a biologically inspired, sequential learning spiking neural classifier (SLSNC) for pattern classification problems. It consists of a two layered neural network and a separate decision block which estimates the predicted class label. Inspired by observations in the neuroscience literature, the input layer employs a new neuron model which converts real valued stimuli into spikes with varying amplitudes and firing times. The intermediate layer neurons are modeled as integrate-and-fire spiking neurons. The decision block identifies that intermediate neuron which fires first and returns the class label associated with that neuron as the predicted class label. The sequential learning algorithm for the spiking neural network automatically determines the network structure from the training samples and adapts its synaptic weights by long term potentiation and long term depression. Performance of SLSNC has been evaluated using a number of benchmark classification problems and the results have been compared with other well-known spiking neural network classifiers in the literature as well as with the standard support vector machine (SVM) with a Gaussian kernel and the fast learning Extreme Learning Machine (ELM) classifiers. The results clearly indicate that the described spiking neural network produces similar or better generalization performance with a smaller network.

KW - 2-Dimensional coding

KW - Pattern classification

KW - Sequential learning

KW - Spiking neural network

UR - http://www.scopus.com/inward/record.url?scp=84939151628&partnerID=8YFLogxK

U2 - 10.1016/j.asoc.2015.06.062

DO - 10.1016/j.asoc.2015.06.062

M3 - Article

VL - 36

SP - 255

EP - 268

JO - Applied Soft Computing

T2 - Applied Soft Computing

JF - Applied Soft Computing

SN - 1568-4946

M1 - 3090

ER -